Verification of Basic Block Schedules Using RTL Transformations

The Android-based networked control system laboratory (NCSLab) is a remote control laboratory that adopts an extensible architecture, mainly including Android mobile devices, MATLAB servers, controllers and test rigs. In order to conduct various simulations and experiments more effectively in NCSLab, the first key issue that needs to be solved is to enable users to design their own control algorithms or functional blocks on the Android client, rather than just using the basic block libraries provided by the system. So, this paper proposes and implements a scheme for Android-based compilation of C-MEX S-functions. With this new feature, users can design personalized algorithm according to their requirements in the form of S-functions, which can be called and executed after being compiled by MATLAB server. Finally, through the experiment validation of the three-degree-of-freedom air bearing spacecraft platform, it is proved that the method of Android-based C-MEX S-functions is reliable and efficient, and this scheme well enhances the functionality and mobility of Android-based NCSLab.

Download Full-text

Machine Learning–enabled Scalable Performance Prediction of Scientific Codes

ACM Transactions on Modeling and Computer Simulation ◽

10.1145/3450264 ◽

2021 ◽

Vol 31 (2) ◽

pp. 1-28

Author(s):

Gopinath Chennupati ◽

Nandakishore Santhi ◽

Phill Romero ◽

Stephan Eidenbenz

Keyword(s):

Machine Learning ◽

Performance Prediction ◽

Prediction Models ◽

Radiation Transport ◽

Discrete Event ◽

Basic Block ◽

Distribution Models ◽

Scientific Application ◽

High Level ◽

Access Patterns

Hardware architectures become increasingly complex as the compute capabilities grow to exascale. We present the Analytical Memory Model with Pipelines (AMMP) of the Performance Prediction Toolkit (PPT). PPT-AMMP takes high-level source code and hardware architecture parameters as input and predicts runtime of that code on the target hardware platform, which is defined in the input parameters. PPT-AMMP transforms the code to an (architecture-independent) intermediate representation, then (i) analyzes the basic block structure of the code, (ii) processes architecture-independent virtual memory access patterns that it uses to build memory reuse distance distribution models for each basic block, and (iii) runs detailed basic-block level simulations to determine hardware pipeline usage. PPT-AMMP uses machine learning and regression techniques to build the prediction models based on small instances of the input code, then integrates into a higher-order discrete-event simulation model of PPT running on Simian PDES engine. We validate PPT-AMMP on four standard computational physics benchmarks and present a use case of hardware parameter sensitivity analysis to identify bottleneck hardware resources on different code inputs. We further extend PPT-AMMP to predict the performance of a scientific application code, namely, the radiation transport mini-app SNAP. To this end, we analyze multi-variate regression models that accurately predict the reuse profiles and the basic block counts. We validate predicted SNAP runtimes against actual measured times.

Download Full-text

Automated Line for Post-Harvest Processing of Root Crops and Potatoes

Agricultural machinery and technologies ◽

10.22314/2073-7599-2020-14-1-22-26 ◽

2020 ◽

Vol 14 (1) ◽

pp. 22-26

Author(s):

A. S. Dorokhov ◽

M. A. Mosyakov ◽

N. V. Sazonov

Keyword(s):

Block Diagram ◽

Basic Block ◽

Potato Tubers ◽

Labor Costs ◽

System Operation ◽

Line System ◽

Post Harvest ◽

Root Crops ◽

Automated Line

In the process of post-harvest processing of root crops and potatoes in Russia, mechanical sortings of various types are used, which allows to separate the material according to the size criterion and removing impurities. The main requirement for this equipment is to ensure the quality and reliability of technological processes for the impurities separation and the root crops separation into fractions with minimal damage. (Research purpose) To improve the quality of potato tubers sorting using an automated line for post-harvest processing of root crops and potatoes, which allows to reduce their damage and ensure high accuracy of separation into fractions by size. (Materials and methods) The authors studied the automated process of root crops post-harvest processing. They developed approaches and basic technical, technological and constructive solutions aimed at improving the efficiency of root crops and potatoes post-harvest processing. To automate the root crops and potatoes processing, the authors installed the universal web camera Logitech HD Pro C920. They created a basic block diagram of the electronic line system operation. (Results and discussion) The authors clarified the size and mass characteristics of potato tubers with a total weight of 38 356 grams of Nevsky variety of the 2019 harvest and their shape coefficient. They developed design documentation. An experimental line was prepared for potato tubers post-harvest sorting with an original circuit diagram of the electronic system operation. The authors substantiated its design and operational-technological parameters. Practical studies of the automated line work were carried out in the Ryazan region on the basis of the Institute of Seed Production and Agrotechnologies – a branch of the Federal Scientific Agroengineering Center VIM. (Conclusions) The authors determined that the developed automated line for root crops and potatoes post-harvest sorting thanks to digital technologies reduced labor costs by eliminating manual sorting, as well as improving the quality of potato tubers and the accuracy of sorting by size to 95-98 percent. It was revealed that damage to potato tubers did not exceed one percent.

Download Full-text

It Is Not Only About Control Dependent Nodes: Basic Block Coverage for Search-Based Crash Reproduction

Search-Based Software Engineering - Lecture Notes in Computer Science ◽

10.1007/978-3-030-59762-7_4 ◽

2020 ◽

pp. 42-57

Author(s):

Pouria Derakhshanfar ◽

Xavier Devroey ◽

Andy Zaidman

Keyword(s):

Basic Block

Download Full-text

Building lifecycle management based on 4D modelling as the main workspace for building risk assessment

E3S Web of Conferences ◽

10.1051/e3sconf/202022402023 ◽

2020 ◽

Vol 224 ◽

pp. 02023

Author(s):

R Kazaryan ◽

N Galaeva ◽

R Avetisyan ◽

Sh Aliev

Keyword(s):

Information Technology ◽

Life Cycle ◽

System Analysis ◽

Planning Process ◽

Block Diagram ◽

Labour Productivity ◽

Development Trend ◽

Basic Block ◽

Mathematical Methods ◽

Element Base

The use of information technology in the management of construction projects has become a decisive factor for the successful completion of projects, taking into account time, quality and financial costs. There are challenges in visualizing the planning process and integrating information between stakeholders. The paper considers some aspects of the development trend of information technology in construction. The element base, including the risks arising during the design and construction, associated with the direct use of computer and mathematical models of the object in the design is considered. The generated information models will provide basic information for the participants in the design process, which ultimately will be the basis of the element base of an effective tool for ensuring project life cycle management. The following methods were used: system analysis, logical-mathematical modelling, systems theory, economic-visual modelling, research methods of operations, economic and mathematical methods. A basic block diagram of 4D modelling is presented to minimize the occurrence of risks during design. The model allows considering the possibility of assessing the duration of the project, the level of labour productivity, as well as visualizing the construction process. The presented analysis indicates the importance of using 4D modelling in relation to the life cycle of the object in order to prevent the possibility of construction risks.

Download Full-text